Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mrauter1/botpipe --skill botpipe-workflow-authoringgit clone --depth 1 https://github.com/mrauter1/botpipeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mrauter1/botpipe/botpipe-workflow-authoring)<a href="https://agentmods.dev/skills/mrauter1/botpipe/botpipe-workflow-authoring"><img src="https://agentmods.dev/badge/skills/mrauter1/botpipe/botpipe-workflow-authoring/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mrauter1/botpipe/botpipe-workflow-authoring"><img src="https://agentmods.dev/badge/skills/mrauter1/botpipe/botpipe-workflow-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.01426 |
| Opus 5.5 | $0.00024 | $0.00570 |
| Sonnet 5.5 | $0.00012 | $0.00285 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
botpipe-workflow-authoring scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Botpipe workflow authoring
Start with docs/authoring.md, docs/prompting.md, and the relevant section of
docs/sdk.md. Load README.md for repository orientation, docs/cli.md for
operator recovery, docs/testing.md before changing tests, and
docs/architecture.md for runtime internals only as needed. Inspect a packaged
workflow and its tests when its pattern is relevant. Use the implementation as
authority if documentation conflicts with it.
Target the Codex-only 2.0 API. Use Provider() by default or Codex()
explicitly. Do not introduce removed 1.x APIs, other provider backends, graph
compilers, route tables, mutable workflow-state engines, a second checkpoint
store, or a legacy persistence path.
Design before code
Answer these as design questions, not mandatory metadata or files:
- What outcome and obligations define success?
- What evidence is authoritative, untrusted, missing, or contradictory?
- Can one capable provider turn finish the work? What concrete benefit requires a durable handoff, separate permission/session, independent review, parallel branch, or human decision?
- What enters and leaves each step, what uncertainty remains, and what may the next step assume?
- How do failure, exhaustion, ambiguity, and unsafe effects recover or escalate?
Keep goals and obligations stable while allowing methods to adapt to discovered evidence. Start with one provider operation. Split only for a clear reliability, authority, concurrency, reuse, or recovery benefit.
Keep control explicit
Use @workflow on an ordinary typed sync or async function. Python owns
sequence, if/match branches, bounded loops, budgets, permissions, joins,
exception handling, and human escalation. Provider turns own semantic judgment,
investigation, and tool-driven work.
Use a nested decorated call for a durable child. Use parallel / aparallel
only for independent required work; a conditional branch selects one path, while
parallel work executes multiple paths and joins them. Give parallel branches
separate sessions and isolate source when concurrent writes or stable review
require it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -41 lines · +2 tokens per session b0827c75d4d7
- 1mo ago Changed · +18 lines · +1 tokens per session 40295d5e8f9e
- 1mo ago Changed · +83 lines · +30 tokens per session 1162ab96f9b0
- 1mo ago Changed · +4 lines fef5469233ae
- 1mo ago Changed · -80 lines · -44 tokens per session a8b0b328d4f1
- 1mo ago Changed · -1 lines cf0d6b4c7f05
- 2mo ago First seen · 148 lines · 72 tokens per session scan A e84b63cd03ab
botpipe-workflow-authoring is a skill published in the GitHub repository mrauter1/botpipe (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,426 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agents-meet-rl
Troubleshooter for agentic-RL training, evaluation, and experiment design on LLM agents (single or multi-agent, multi-turn, tool-augmented). Routes a user's symptom to fixes anchored in the corpus. TRIGGER when: user is training, evaluating, or designing experiments for an RL-trained LLM agent; symptoms like reward…
goal-oriented
MUST use for ANY user request. This is a rigid requirement that applies to all tasks and conversations.
planning
MUST use after prompt-enhancer. Create implementation plan with MECE decomposition, dependency analysis, risk assessment, and mandatory plan-review.
mvp-first
Use when user requests complex systems involving multiple modules or subsystems - like 'build a XX system', 'design XX architecture', or 'implement XX with multiple features'. Triggers to prevent over-engineering before validating core assumptions.
ddd-tactical-design
Use when implementing domain logic, designing aggregates, entities, value objects, repositories, domain services, domain model design, ensuring data consistency, or when user mentions 'aggregate design', 'aggregate root', 'entity vs value object', 'domain event', 'repository pattern', 'domain service', 'data…
prompt-enhancer
MUST use before task execution. Clarify vague requirements, explore solutions, and ensure full understanding.